© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 59178
    Prev
    Next
    INDEX
    Explanations

    formulas and code

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron activates on spreadsheet‐formula syntax, i.e. function names, operators, and cell‐reference tokens.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Olvid
    -0.84
    Imágenes
    -0.78
    Composición
    -0.78
    近い
    -0.77
    Característica
    -0.76
    Atentamente
    -0.76
    Pued
    -0.76
    Puede
    -0.75
     darauf
    -0.75
     unsatisfied
    -0.75
    POSITIVE LOGITS
    ナー
    0.80
     परिवार
    0.79
     מיט
    0.78
     Sheet
    0.77
    LEFT
    0.75
    ⬇
    0.75
     Consortium
    0.75
     Chronic
    0.73
    &+
    0.73
     hornear
    0.72
    Activations Density 0.096%

    No Known Activations